Innovations in Information and Communication Technology


Series: Innovations in Information and Communication Technology

Advanced Deep Learning with Python: To Design, Develop, and Enhance Advanced Neural Network Models

Suman Rajest S, Salvatore Moccia, Bhopendra Singh, Regin R (Editors)


Describes the advances of machine learning, guiding you through setting up with ICT frameworks.

Represents ICT based Framework for Data Science and Machine Learning real-life case studies and examples

Updated and expanded to reflect the latest developments, Statistical Methods for Survival Data Analysis and Machine Learning Applications


About this Book

Neural networks are one of the most beautiful programming paradigms ever invented. In the conventional programming approach, we tell the computer what to do, breaking big problems into many small, precisely defined tasks that the computer can easily perform. By contrast, in a neural network, we don't tell the computer how to solve our problem. Instead, it learns from observational data, figuring out its solution to the problem at hand. Automatically learning from data sounds promising. It is possible to understand many conventional machine learning models as special cases of neural networks. In the first two chapters, a focus is placed on understanding the link between conventional machine learning and neural networks. Special neural networks are seen as support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommendation systems. Deep neural networks and deep learning achieve outstanding performance on many important problems in computer vision, speech recognition, and natural language processing. They're being deployed on a large scale by companies such as Google, Microsoft, and Facebook. The purpose of this book is to help you master the core concepts of neural networks, including modern techniques for deep learning. After working through the book, you will have written code that uses neural networks and deep learning to solve complex pattern recognition problems. And you will have a foundation to use neural networks and deep learning to attack your devising problems. One conviction underlying the book is that it's better to obtain a solid understanding of neural networks' core principles and deep learning, rather than a hazy understanding of a long laundry list of ideas.

Topics Covered

  • Deep Learning
  • Supervised and Unsupervised Learning
  • Machine Learning Methods
  • Machine Learning with Schematic Neural Networks
  • Artificial Intelligence
  • Neural Networks
  • Recurrent Neural Networks
  • Training Deep Neural Networks
  • Convolutional Neural Networks
  • Attention Mechanism
  • Likelihood Ratios
  • Image classification
  • Image Retrieval
  • Data Science
  • Exploratory Data Analysis
  • Data Visualization
  • Regression
  • Linear Regression
  • Logistic Regression
  • Support Vector Machines
  • MATLAB